AI BENCHY Compare
Anthropic: Claude Sonnet 4.6 vs Google: Gemini 2.5 Flash
Linganisha:
Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-03-03
| Kipimo | Anthropic: Claude Sonnet 4.6 none Toleo: 2026-02-17 | Google: Gemini 2.5 Flash medium Toleo: 2025-06-17 |
|---|---|---|
| Nafasi | #22 | #16 |
| Wastani wa alama | 6.36 | 7.05 |
| Uthabiti | 9.50 | 9.39 |
| Gharama kwa matokeo | 1.325 | 2.762 |
| Jumla ya gharama | $0.106 | $0.249 |
| Majaribio sahihi | ||
| Kiwango cha kupita kwa kila jaribio | 59.5% | 69.1% |
| Majaribio yasiyo thabiti | 1 | 1 |
| Tokeni za matokeo | 2,637 | 975 |
| Tokeni za hoja | 0 | 96,701 |
Alama dhidi ya gharama ya jumla
Mgawanyo wa kategoria
| Mbinu za kupinga AI | Alama | Uthabiti | Kiwango cha kupita kwa kila jaribio | Majaribio yasiyo thabiti | Majaribio sahihi | Tokeni za matokeo | Tokeni za hoja |
|---|---|---|---|---|---|---|---|
| Anthropic: Claude Sonnet 4.6 | 4.00 | 10.00 | 33.3% | 0 | 1,199 | 0 | |
| Google: Gemini 2.5 Flash | 7.33 | 10.00 | 66.7% | 0 | 249 | 8,832 |
| Uchanganuzi na uchimbaji wa data | Alama | Uthabiti | Kiwango cha kupita kwa kila jaribio | Majaribio yasiyo thabiti | Majaribio sahihi | Tokeni za matokeo | Tokeni za hoja |
|---|---|---|---|---|---|---|---|
| Anthropic: Claude Sonnet 4.6 | 10.00 | 10.00 | 100.0% | 0 | 252 | 0 | |
| Google: Gemini 2.5 Flash | 9.88 | 10.00 | 100.0% | 0 | 279 | 2,325 |
| Mahususi kwa domeni | Alama | Uthabiti | Kiwango cha kupita kwa kila jaribio | Majaribio yasiyo thabiti | Majaribio sahihi | Tokeni za matokeo | Tokeni za hoja |
|---|---|---|---|---|---|---|---|
| Anthropic: Claude Sonnet 4.6 | 7.00 | 10.00 | 66.7% | 0 | 54 | 0 | |
| Google: Gemini 2.5 Flash | 4.00 | 7.21 | 55.6% | 1 | 18 | 80,702 |
| Ufuataji wa maagizo | Alama | Uthabiti | Kiwango cha kupita kwa kila jaribio | Majaribio yasiyo thabiti | Majaribio sahihi | Tokeni za matokeo | Tokeni za hoja |
|---|---|---|---|---|---|---|---|
| Anthropic: Claude Sonnet 4.6 | 5.50 | 10.00 | 50.0% | 0 | 90 | 0 | |
| Google: Gemini 2.5 Flash | 7.00 | 9.91 | 50.0% | 0 | 69 | 1,203 |
| Puzzle Solving | Alama | Uthabiti | Kiwango cha kupita kwa kila jaribio | Majaribio yasiyo thabiti | Majaribio sahihi | Tokeni za matokeo | Tokeni za hoja |
|---|---|---|---|---|---|---|---|
| Anthropic: Claude Sonnet 4.6 | 5.00 | 7.68 | 44.4% | 1 | 595 | 0 | |
| Google: Gemini 2.5 Flash | 7.00 | 10.00 | 66.7% | 0 | 126 | 2,499 |
| Mwito wa zana | Alama | Uthabiti | Kiwango cha kupita kwa kila jaribio | Majaribio yasiyo thabiti | Majaribio sahihi | Tokeni za matokeo | Tokeni za hoja |
|---|---|---|---|---|---|---|---|
| Anthropic: Claude Sonnet 4.6 | 10.00 | 10.00 | 100.0% | 0 | 447 | 0 | |
| Google: Gemini 2.5 Flash | 10.00 | 10.00 | 100.0% | 0 | 234 | 1,140 |
Ulinganisho wa haraka
Badilisha jozi ya ulinganisho
Claude Sonnet 4.6nonevsGrok 4.1 FastmediumClaude Sonnet 4.6nonevsKimi K2.5mediumGemini 2.5 FlashmediumvsGPT-5.3 ChatnoneClaude Sonnet 4.6nonevsSeed-2.0-MinimediumGemini 2.5 FlashmediumvsGPT-5.2 ChatnoneClaude Sonnet 4.6nonevsMiMo-V2-FlashmediumClaude Sonnet 4.6nonevsQwen3.5-122B-A10BmediumClaude Sonnet 4.6nonevsQwen3.5-35B-A3BmediumClaude Sonnet 4.6nonevsGPT-5 NanomediumClaude Sonnet 4.6nonevsGemini 3.1 Flash Lite PreviewmediumClaude Sonnet 4.6nonevsQwen3.5-FlashmediumClaude Sonnet 4.6nonevsGPT-5.2medium